© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 80625
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and their formatting in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    oulos
    -0.07
    amus
    -0.06
    onis
    -0.06
    ActionCreators
    -0.06
    ton
    -0.06
     Atlas
    -0.06
     prom
    -0.06
    enheim
    -0.05
    äng
    -0.05
    Atlas
    -0.05
    POSITIVE LOGITS
    https
    0.13
     https
    0.11
    http
    0.09
    =https
    0.09
    _https
    0.09
     http
    0.09
    Https
    0.08
    ://
    0.08
    	http
    0.08
    cka
    0.07
    Activations Density 0.005%

    No Known Activations